BS Chapter4 2021 Discrete Probability Distribution Binomial Hyper Poisen 22

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 40

Lecture 4

Discrete
Probability Distribution
© 2011 Pearson Education, Inc
Probability Distribution
• A frequency distribution describes a specific sample or dataset. It’s the number of
times each possible value of a variable occurs in the dataset.The term “probability
distribution” refers to any statistical function that dictates all the possible outcomes
of a random variable within a given range of values. One of the most common
examples of a probability distribution is the Normal distribution. However, there are
other major categories of probability distributions – Chi-square distribution,
 Binomial distribution, and Poisson distribution.
• A probability distribution is a mathematical function that describes the probability
of different possible values of a variable. It is a mathematical description of a
random phenomenon in terms of its sample space and the probabilities of events. 
WikipediaProbability distributions are often depicted using graphs or probability
tables.
• On the other hand, the term “probability distribution formula” covers the formula of
parameters of a probability distribution – mean, standard deviation, skewness, and
kurtosis.
© 2011 Pearson Education, Inc
Discrete probability distribution: A distribution is called a discrete probability distribution, where the set of outcomes are discrete in nature.

For example, if a dice is rolled, then all the possible outcomes are discrete and give a mass of outcomes. It is also known as the probability mass

function.

Continuous probability distribution: is the probability distribution of a continuous variable. A continuous variable can have any value between its

lowest and highest values. Therefore, continuous probability distributions include every number in the variable’s range. The probability that a

continuous variable will have any specific value is so infinitesimally small that it’s considered to have a probability of zero. However, the probability

that a value will fall within a certain interval of values within its range is greater than zero.

Probability density functions: A probability density function (PDF) is a mathematical function that describes a continuous probability distribution.

It provides the probability density of each value of a variable, which can be greater than one. A probability density function can be represented as an

equation or as a graph.
Discrete Probability Distribution

Probabiloity Mass Function

Discrete probability distribution: A distribution is called a discrete probability distribution, where the set of
outcomes are discrete in nature. For example, if a dice is rolled, then all the possible outcomes are discrete and give a

mass of outcomes. It is also known as the probability mass function.


Discrete Probability Distribution

Probabiloity Mass Function


Probability Distribution
Discrete Probability Distribution
© 2011 Pearson Education, Inc
n!
 p r q nr
r! (n - r)!

  np
   np(   p )
Binomial Distribution
Assumptions:
1. Trials follow Bernoulli process – two possible outcomes
ex- head n Tail.
2. Probabilities stay the same from one trial to the next
3. Trials are statistically independent
4. Number of trials is a positive integer
Binomial Distribution
Binomial Trial:
If random experiment is repeated many times. Each trial is independent.
There are only two possible outcomes. One is success and failure.
• The binomial distribution is the probability distribution formula that
summarizes the likelihood of an event occurs either A win, B loses or vice-
versa under given set parameters or assumptions. However, there is an
underlying assumption of the binomial distribution where there is only one
outcome is possible for each trial, either success or loss. And each trial in
itself is mutually exclusive from another one. For ex,
In examination----------Pass or Fail, Tossing a coin-----------Head or not head.
Rolling a die--------------2 or not 2., Drawing a card----------King or not king.
Binomial Distribution. n = Number of trials
p = Probability of successive outcomes.
q = Probability of failure outcomes.
x = Number of successes.
• p + q =1   np
• Mean = np and Variance = npq    np(   p )
Binomial Distribution
• There are certain steps and rules to meet the specific criteria of Binomial Distribution models in
order to use the formula.
Step 1: Fixed Trials
• In this course of action, there is a certain set of a fixed number of trials which can’t be altered in the
course of the whole process. The number of trials in the binomial probability formula is represented
by the letter “n”. In our case, flips a coin, free throws, wheel spins are the fixed number of trials.

Step 2: Independent Trials


• Independent Trial is another condition of a binomial probability in which trials are independent of
each other where the outcome of one trial doesn’t impact much more on the subsequent trials.

• If we take an example where independent trials, maybe tossing a coin or rolling dice, is independent
of the subsequent events.

Step 3: Fixed Probability of success


• In this type of distribution, the probability of getting success remain the same for all trials. For
example, if we toss a coin, the probability of an outcome of every event, either head or tail, is 0.5
since there are two possible outcomes.

Step 4: Two Mutually exclusive Outcomes


• In this distribution, there are only two types of mutually exclusive outcomes that exist, either success
or failure. Where success has been defined in a positive term. The purpose of the trial is to validate
what we have defined as a success. Either it is positive or negative.
Binomial Distribution
Example #1
A coin is flipped 10 times. Calculate the probability of getting 5 heads using a
Binomial distribution formula.

Solution: Given n=10, r=x= 5, p(x) = prob of success = 0.5


Probability is calc
n!
 p r q nr
r! (n - r)!
P(x=5) = (10! / (5! * (10 – 5)!)) * (0.5)^5 * (1 – 0.5)^(10 – 5)
P(x=5) = (10! / (5! * 5!)) * (0.5)^5 * (0.5)^5
P(x=5) = 0.2461
The probability of getting exactly 5 successes is 0.2461
Binomial Distribution
Example #2
In a study, it is found that 70% of people who purchase pet
insurance are mostly women. If we randomly select 9 pet
insurance owners. What is the probability, out of the 7 will be
women?

Solution: n=9, r = x =7, p(x) = prob of success = 0.7 (70%)


Probability is calculated using the binomial distribution formula as
given below.
n!
 p r q nr
r! (n - r)!
P(x=7) = (9! / (7! * (9 – 7)!)) * (0.7)^7 * (1 – 0.7)^(9 – 7)
P(x=7) = (9! / (7! * 2!)) * (0.7)^7 * (0.3)^2
P(x=7) = 0.2668
Binomial Distribution
Example #3
Last year in the survey of Auto car, it was found that 70% of
buyers of sports cars are men. If 10 sports car owners are
randomly selected. What is the probability, out of the 6 will be
men?

Solution:
Probability is calculated using the binomial distribution formula as
given below. n!
 p r q nr
r! (n - r)!
P(x=5) = (10! / (6! * (10 – 6)!)) * (0.7)^6 * (1 – 0.7)^(10 – 6)
P(x=5) = (10! / (6! * 4!)) * (0.7)^6 * (0.3)^4
P(x=5) = 0.2001
Example #4
n! r nr
 p q
r! (n - r)!

© 2011 Pearson Education, Inc


© 2011 Pearson Education, Inc
Binomial Distribution

N = 5, p = 0.50

0.35
0.30
0.25
P (r)

0.20
0.15
0.10
0.05
0.00
1 2 3 4 5 6
(r) Number of Succes s es
Geometric Distribution

Definition

Geometric distribution can be defined as a discrete probability distribution that represents the probability of getting the first success after having a consecutive number

of failures.

A geometric distribution can have an indefinite number of trials until the first success is obtained.

Geometric distribution is a type of discrete probability distribution that represents the probability of the number of successive failures before a success is obtained in a

Bernoulli trial.

A Bernoulli trial is an experiment that can have only two possible outcomes, ie., success or failure. In other words, in a geometric distribution, a Bernoulli trial is

repeated until a success is obtained and then stopped.

Geometric distribution is widely used in several real-life scenarios. For example, in financial industries, geometric distribution is used to do a cost-benefit analysis to

estimate the financial benefits of making a certain decision.

What is Geometric Distribution?

Geometric distribution is a type of probability distribution that is based on three important assumptions.

• The trials being conducted are independent.

• There can only be two outcomes of each trial - success or failure.

• The success probability, denoted by p, is the same for each trial.

Example: Suppose a dice is repeatedly rolled until "3" is obtained. Then the probability of getting "3" is p = 1 / 6 and the random variable, X, can take on a value of 1,

2, 3, ...., until the first success is obtained. This is an example of a geometric distribution with p = 1 / 6.

© 2011 Pearson Education, Inc


© 2011 Pearson Education, Inc
Example 1: If a patient is waiting for a suitable blood donor and the probability that the selected donor will be a match is 0.2, then find the expected number of donors who will

be tested till a match is found including the matched donor.

Solution: As we are looking for only one success this is a geometric distribution.

p = 0.2

E[X] = 1 / p = 1 / 0.2 = 5

Answer: The expected number of donors who will be tested till a match is found is 5 (including the donor).

Example 2: Suppose you are playing a game of darts. The probability of success is 0.4. What is the probability that you will hit the bullseye on the third try?

Solution: As we are looking for the first success, thus, geometric distribution has to be used.

p = 0.4

P(X = x) = (1 - p)x - 1p

P(X = 3) = (1 - 0.4)3 - 1(0.4)

P(X = 3) = (0.6)2(0.4) = 0.144

Answer: The probability that you will hit the bullseye on the third try is 0.144

Example 3: A light bulb manufacturing factory finds 3 in every 60 light bulbs defective. What is the probability that the first defective light bulb with be found when the 6th one is tested?

Solution: As the probability of the first defective light bulb needs to be determined hence, this is a geometric distribution.

p = 3 / 60 = 0.05

P(X = x) = (1 - p)x - 1p

P(X = 6) = (1 - 0.05)6 - 1(0.05)

P(X = 6) = (0.95)5(0.05)

P(X = 6) = 0.0386

Answer: The probability that the first defective light bulb is found on the 6th trial is 0.0368
© 2011 Pearson Education, Inc
© 2011 Pearson Education, Inc
Poisson Distribution
• In probability theory and statistics, the Poisson distribution is
a discrete probability distribution that expresses the
probability of a given number of events occurring in a fixed
interval of time or space if these events occur with a known
constant mean rate and independently of the time since the
last event.

© 2011 Pearson Education, Inc


Poisson Distribution

© 2011 Pearson Education, Inc


© 2011 Pearson Education, Inc
Hypergeometric Distribution is basically a discrete probability distribution in statistics. It is very similar to binomial distribution and we can say that with confidence that

binomial distribution is a great approximation for hypergeometric distribution only if the 5% or less of the population is sampled. If we have random draws, hypergeometric

distribution is a probability of successes without replacing the item once drawn. But in a binomial distribution, the probability is calculated with replacement. For example, You

have a basket which has N balls out of which “n” are black and you draw “m” balls without replacing any of the balls. So hypergeometric distribution is the probability

distribution of the number of black balls drawn from the basket. Formula For Hypergeometric Distribtn

Probability of Hypergeometric Distribution =

• x or k – No. of “successes” in the sample

• K – No. of “successes or defective” in Population

• N – Population size

• n – Sample Size

Hypergeometric distribution is a probability of distribution which is very similar to a binomial distribution with the difference that there is no replacement allowed. In order to

perform this type of experiment or distribution, there are several criteria which need to be met.

First and the foremost requirement is that data collected should be discrete in nature.

Each pick or draw should not be replaced by another because whenever a random variable is drawn without replacement, then it is not independent and has relation to what is

drawn earlier.

There must be 2 sets of different group and you want to know the probability of a specific number of members of one group. For example, in the voting example, we have male

and females. In bag example, we have a yellow and black group.


OR
Example #1

Let say you live in a very small town which has 75 females and 95 males. Now there was voting which took place in your

town and everyone voted. A sample of 20 voters was selected randomly. You want to calculate what is the probability that

exactly 12 of these voters were male voters.

Hypergeometric Distribution is calculated

Probability of Hypergeometric Distribution =

Probability of getting 12 male voters = [C(95,12) * C(75, 8)] / [C(170,20)] = ?

P(12) M voters = ({(95!) / [(95-12)! (12)!] } * {(75!) / [(75-8)! (8)!)]} ) / {[(170!) / (20! *150!)]}

Prob of 12 male voters = ({(95!) / [(83!) (12!)]} * {(75!) / [(8!)(63!)]}) / {(170!) / [(150!) (20! )]}

Probability of getting 12 male voters = 0.1766 ANS


Calculation
• 95 ! = 1.03299785 e148
• 83 ! = 3.94552397 e124
• 12 ! = 479001600
• (83!)(12 !) = 1.88991229e133
• (12 !) / [(83!)(12 !)] = 2.53451761e125

© 2011 Pearson Education, Inc


Hypergeometric Distribution
Example #2

Let Say you have a deck of colored cards which has 30 cards out of which 12 are black and 18 are yellow.

You have drawn 5 cards randomly without replacing any of the cards. Now you want to find the probability

of exactly 3 yellow cards is drawn.

Solution:

Probability of Hypergeometric Distribution = C(K,k) * C((N – K), (n – k)) / C(N,n)

You might also like